Two-step machine learning enables optimized nanoparticle synthesis
Source abstract
Abstract
Abstract In materials science, the discovery of recipes that yield nanomaterials with defined optical properties is costly and time-consuming. In this study, we present a two-step framework for a machine learning-driven high-throughput microfluidic platform to rapidly produce silver nanoparticles with the desired absorbance spectrum. Combining a Gaussian process-based Bayesian optimization (BO) with a deep neural network (DNN), the algorithmic framework is able to converge towards the target spectrum after sampling 120 conditions. Once the dataset is large enough to train the DNN with sufficient accuracy in the region of the target spectrum, the DNN is used to predict the colour palette accessible with the reaction synthesis. While remaining interpretable by humans, the proposed framework efficiently optimizes the nanomaterial synthesis and can extract fundamental knowledge of the relationship between chemical composition and optical properties, such as the role of each reactant on the shape and amplitude of the absorbance spectrum.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Computational Drug Discovery Methods · Gold and Silver Nanoparticles Synthesis and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (48)
Show source-provided references
1. Altae-Tran, H., Ramsundar, B., Pappu, A. S. & Pande, V. Low data drug discovery with one-shot learning. ACS Cent. Sci. 3, 283–293 (2017).10.1021/acscentsci.6b00367 ↗
2. Chen, H., Engkvist, O., Wang, Y., Olivecrona, M. & Blaschke, T. The rise of deep learning in drug discovery. Drug Discov. Today 23, 1241–1250 (2018).10.1016/j.drudis.2018.01.039 ↗
3. Erickson, B. J., Korfiatis, P., Akkus, Z. & Kline, T. L. Machine learning for medical imaging. RadioGraphics 37, 505–515 (2017).10.1148/rg.2017160130 ↗
4. Xie, T. & Grossman, J. C. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties. Phys. Rev. Lett. 120, 145301 (2018).10.1103/PhysRevLett.120.145301 ↗
5. Yamawaki, M., Ohnishi, M., Ju, S. & Shiomi, J. Multifunctional structural design of graphene thermoelectrics by Bayesian optimization. Sci. Adv. 4, eaar4192 (2018).10.1126/sciadv.aar4192 ↗
6. Butler, K. T., Davies, D. W., Cartwright, H., Isayev, O. & Walsh, A. Machine learning for molecular and materials science. Nature 559, 547–555 (2018).10.1038/s41586-018-0337-2 ↗
7. Olivecrona, M., Blaschke, T., Engkvist, O. & Chen, H. Molecular de-novo design through deep reinforcement learning. J. Cheminform. 9, 48 (2017).10.1186/s13321-017-0235-x ↗
8. Nash, W., Drummond, T. & Birbilis, N. A review of deep learning in the study of materials degradation. npj Mater. Degrad. 2, 37 (2018).10.1038/s41529-018-0058-x ↗
9. Himanen, L., Geurts, A., Foster, A. S. & Rinke, P. Data‐driven materials science: status, challenges and perspectives. Adv. Sci. 6, 1900808 (2019).10.1002/advs.201900808 ↗
10. Trivedi, V. et al. A modular approach for the generation, storage, mixing, and detection of droplet libraries for high-throughput screening. Lab Chip 10, 2433–2442 (2010).10.1039/c004768f ↗
11. Knauer, A. et al. Screening of plasmonic properties of composed metal nanoparticles by combinatorial synthesis in micro-fluid segment sequences. Chem. Eng. J. 227, 80–89 (2013).10.1016/j.cej.2012.10.008 ↗
12. Lignos, I. et al. Synthesis of cesium lead halide perovskite nanocrystals in a droplet-based microfluidic platform: fast parametric space mapping. Nano Lett. 16, 1869–1877 (2016).10.1021/acs.nanolett.5b04981 ↗
13. Epps, R. W., Felton, K. C., Coley, C. W. & Abolhasani, M. Automated microfluidic platform for systematic studies of colloidal perovskite nanocrystals: towards continuous nano-manufacturing. Lab Chip 17, 4040–4047 (2017).10.1039/C7LC00884H ↗
14. Bezinge, L., Maceiczyk, R. M., Lignos, I., Kovalenko, M. V. & Demello, A. J. Pick a color MARIA: adaptive sampling enables the rapid identification of complex perovskite nanocrystal compositions with defined emission characteristics. ACS Appl. Mater. Interfaces 10, 18869–18878 (2018).10.1021/acsami.8b03381 ↗
15. Salley, D. et al. A nanomaterials discovery robot for the Darwinian evolution of shape programmable gold nanoparticles. Nat. Commun. 11, 2771 (2020).10.1038/s41467-020-16501-4 ↗
16. Shabanzadeh, P., Yusof, R. & Shameli, K. Neural network modelling for prediction size of silver nanoparticles in montmorillonite/starch synthesis by chemical reduction method. Dig. J. Nanomater. Bios. 9, 1699–1711 (2014).
17. Thanh, N. T. K., Maclean, N. & Mahiddine, S. Mechanisms of nucleation and growth of nanoparticles in solution. Chem. Rev. 114, 7610–7630 (2014).10.1021/cr400544s ↗
18. Lee, J., Yang, J., Kwon, S. G. & Hyeon, T. Nonclassical nucleation and growth of inorganic nanoparticles. Nat. Rev. Mater. 1, 16034 (2016).10.1038/natrevmats.2016.34 ↗
19. Yuan, B. et al. Machine-learning-based monitoring of laser powder bed fusion. Adv. Mater. Technol. 3, 1800136 (2018).10.1002/admt.201800136 ↗
20. Kumar, J. et al. Machine learning enables polymer cloud-point engineering via inverse design. npj Comput. Mater. 5, 73 (2019).10.1038/s41524-019-0209-9 ↗
21. Voznyy, O. et al. Machine learning accelerates discovery of optimal colloidal quantum dot synthesis. ACS Nano 13, 11122–11128 (2019).10.1021/acsnano.9b03864 ↗
22. Gonzalez, J., Dai, Z., Hennig, P. & Lawrence, N. Batch Bayesian optimization via local penalization. In: Proc. 19th International Conference on Artificial Intelligence and Statistics. 51, 648–657 (2016).
23. Dai, Z. et al. GPyOpt: a Bayesian optimization framework in python. http://github.com/SheffieldML/GPyOpt (2016).
24. Shuford, K. L., Ratner, M. A. & Schatz, G. C. Multipolar excitation in triangular nanoprisms. J. Chem. Phys. 123, 114713 (2005).10.1063/1.2046633 ↗
25. Aherne, D., Ledwith, D. M., Gara, M. & Kelly, J. M. Optical properties and growth aspects of silver nanoprisms produced by a highly reproducible and rapid synthesis at room temperature. Adv. Funct. Mater. 18, 2005–2016 (2008).10.1002/adfm.200800233 ↗
26. Burger et al. A mobile robotic chemist. Nature 583, 237–241 (2020).10.1038/s41586-020-2442-2 ↗
27. Li, Z. et al. Robot-accelerated perovskite investigation and discovery. Chem. Mater. 32, 5650–5663 (2020).10.1021/acs.chemmater.0c01153 ↗
28. Tshitoyan, V. et al. Unsupervised word embeddings capture latent knowledge from materials science literature. Nature 571, 95–98 (2019).10.1038/s41586-019-1335-8 ↗
29. Umehara, M. Analyzing machine learning models to accelerate generation of fundamental materials insights. npj Comput. Mater. 5, 34 (2019). & al.10.1038/s41524-019-0172-5 ↗
30. Epps, R. W. et al. Artificial chemist: an autonomous quantum dot synthesis bot. Adv. Mater. 32, 2001626 (2020).10.1002/adma.202001626 ↗
31. Williams, T., McCullough, K. & Lauterbach, J. A. Enabling catalyst discovery through machine learning and high-throughput experimentation. Chem. Mater. 32, 157–165 (2020).10.1021/acs.chemmater.9b03043 ↗
32. Häse, F., Roch, L. M., Kreisbeck, C. & Aspuru-Guzik, A. Phoenics: a Bayesian optimizer for chemistry. ACS Cent. Sci. 4, 1134–1145 (2018).10.1021/acscentsci.8b00307 ↗
33. Wang, H. & Li, J. Adaptive Gaussian process approximation for Bayesian inference with expensive likelihood functions. Neural Comput 30, 3072–3094 (2018).10.1162/neco_a_01127 ↗
34. Sakamoto, Y., Ishiguro, M. & Kitagawa, G. Akaike information criterion statistics (D. Reidel, Dordrecht, 1986).
35. Schwarz, G. Estimating the dimension of a model. Ann. Stat. 6, 461–464 (1978).10.1214/aos/1176344136 ↗
36. Wolpert, D. H. & Macready, W. G. Coevolutionary free lunches. IEEE Trans. Evolut. Comput. 9, 721–735 (2005).10.1109/TEVC.2005.856205 ↗
37. Rohr, B. et al. Benchmarking the acceleration of materials discovery by sequential learning. Chem. Sci. 11, 2696–2706 (2020).10.1039/C9SC05999G ↗
38. Jones, D. R. A taxonomy of global optimization methods based on response surfaces. J. Glob. Optim. 21, 345–383 (2001).10.1023/A:1012771025575 ↗
39. Rasmussen C. E. Gaussian processes in machine learning. In: Advanced Lectures on Machine Learning (Springer-Verlag, Berlin Heidelberg, 2004).10.1007/978-3-540-28650-9_4 ↗
40. Wang, Z. L., Ogawa, T. & Adachi, Y. Influence of algorithm parameters of Bayesian optimization, genetic algorithm, and particle swarm optimization on their optimization performance. Adv. Theory Simul. 2, 1900110 (2019).10.1002/adts.201900110 ↗
41. Frazier, P. I. Bayesian optimization. In Recent Advances in Optimization and Modeling of Contemporary Problems, 255–278 (2018).10.1287/educ.2018.0188 ↗
42. Stathakis, D. How many hidden layers and nodes? Int. J. Remote Sens. 30, 2133–2147 (2009).10.1080/01431160802549278 ↗
43. Goodfellow, I., Bengio, Y. & Courville, A. Deep Learning: Adaptive Computation and Machine Learning (MIT Press, Cambridge, 2016).
44. Lundberg, S. & Lee, S. I. A unified approach to interpreting model predictions. In Proc. 31st Conference on Neural Information Processing Systems (NIPS, 2017).
45. Singh, A. K. et al. Nonlinear optical properties of triangular silver nanoparticles. Chem. Phys. Lett. 481, 94–98 (2009).10.1016/j.cplett.2009.09.045 ↗
46. Potara, M., Gabudean, A.-M. & Astilean, S. Solution-phase, dual LSPR-SERS plasmonic sensors of high sensitivity and stability based on chitosan-coated anisotropic silver nanoparticles. J. Mater. Chem. 21, 3625–3633 (2011).10.1039/c0jm03329d ↗
47. Draine, B. T. & Flatau, P. J. Discrete dipole approximation for scattering calculations. J. Opt. Soc. Am. A 11, 1491–1499 (1994).10.1364/JOSAA.11.001491 ↗
48. Johnson, P. B. & Christy, R. W. Optical constants of the nobel metals. Phys. Rev. B 6, 4370–4379 (1972).10.1103/PhysRevB.6.4370 ↗